View Task Intelligence prediction history
Summarize
Summary of View Task Intelligence Prediction History
The Predictor Result table in ServiceNow allows users to access historical predictions related to Task Intelligence. This includes details such as predicted language, predicted and actual values, and prediction confidence, enabling users to monitor model performance effectively.
Show less
Key Features
- Access to the Predictor Result table via All > Task Intelligence for Customer Service > History.
- Role-based access for Task Intelligence admins and Customer Service managers.
- Captures case categorization feedback when case status changes to Closed, provided the predicted field differs from the actual case field.
- Supports various categorization solutions: email, case, and interaction categorization.
- Stores critical data points including predicted output and input values, final input and output values, and predicted confidence percentage.
Key Outcomes
Customers can leverage the historical prediction data to assess and improve model performance. Understanding categorization feedback helps enhance the accuracy of predictions. Additionally, managing email sentiment replies by deactivating the Predict Sentiment for Cases action can prevent duplicate entries in the Predictor Result table.
View details about historical predictions in the Predictor Result [ml_predictor_results] table.
Viewing prediction data
Navigate to to view the Predictor Result list.
- Task Intelligence admin [sn_csm_ml_task.ti_admin]
- Customer Service manager [sn_customerservice_manager]
- Case categorization is active.
- The predicted field value is different from the case field value.
Categorization feedback works for record categorization solutions and for solutions with and without attachments. Email categorization solutions are trained using data from the Email [sys_email] table. Case categorization solutions are trained using data from the Case [sn_customerservice_case] table or from tables that extend the Case table. Interaction categorization solutions are trained using data from the Interaction [interaction] table.
- When email information is used for prediction, the final input values remain empty.
- When attachment information is used for prediction, the attachment sys_ids are not included in the final input values.
- Predicted Output Value Name
- Predicted Input Value Names
- Predicted Output Value
- Predicted Input Values
- Final Input Value
- Final Output Value
- Predicted Confidence (percentage)
- The Final Input Value remains empty because it is not expected that the agent will modify the values of the email, such as subject and body.
- The final value in the Predicted Output Value is stored in the Final Output Value once the case is closed.
- The values from the fields defined in Predicted Input Value Names are stored in Final Input Value.
- The final value in the Predicted Output Value is stored in the Final Output Value once the case is closed.
Email sentiment replies
Duplicate entries can be posted in the Predictor Result table for email sentiment replies. To help prevent these duplicate entries, deactivate the Predict Sentiment for Cases inbound email action. For more information, see Inbound email actions.